Menu
Validates project.yaml is well-formed. Checks required fields, valid values, resolvable paths, and detects typos.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Generates a context-specific audit brief and executes review via code-reviewer agent. Usable standalone or as a building block within other skills.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Full SDLC workflow - from task to PR. Plans, audits adversarially, implements, runs quality gates, and opens a PR.
Generates a PR description from the current branch diff and project conventions. Output is a ready-to-use markdown body.
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
Validates code against all project architecture conventions. Reads project.yaml to determine applicable checks and runs them. Replaces individual check-* skills.
| name | check-config |
| description | Validates project.yaml is well-formed. Checks required fields, valid values, resolvable paths, and detects typos. |
Read-only validation. Reports config errors with field path and suggestion.
Look for project.yaml in the project's config directory (.ai/, .claude/,
.cursor/, or whichever directory contains the skills/agents symlinks).
If file does not exist, report and stop.
These fields must be present and non-empty:
runtime - one of: deno, node, go, python, rustarchitecture.pattern - one of: port-adapter, layered, hexagonal, mvc, nonequality_gates.commands.formatquality_gates.commands.lintquality_gates.commands.testReport each missing field with its expected type/values.
For each path field, verify the directory exists:
test -d "{architecture.ports_dir}" || echo "MISSING: architecture.ports_dir -> {value}"
test -d "{architecture.adapters_dir}" || echo "MISSING: architecture.adapters_dir -> {value}"
test -d "{architecture.domain_dir}" || echo "MISSING: architecture.domain_dir -> {value}"
test -d "{testing.test_dir}" || echo "MISSING: testing.test_dir -> {value}"
test -d "{testing.mock_dir}" || echo "MISSING: testing.mock_dir -> {value}"
Skip fields that are absent from config (optional).
For each command in quality_gates.commands, verify the base tool exists:
which deno || which npm || which pnpm || which go # based on runtime
If the configured command references a tool not available on PATH, warn.
Valid top-level keys: config_dir, runtime, architecture, conventions, quality_gates, testing, git.
Flag any top-level key not in this list as a likely typo.
Valid conventions sub-keys: naming, error_handling, barrel_exports, domain_purity, observability.
Flag unknown sub-keys.
## Config Validation
| Field | Status | Issue |
|---|---|---|
| runtime | OK | - |
| architecture.ports_dir | WARN | Directory does not exist: src/application/ |
| quality_gates.commands.audit | OK | - |
| conventions.observabilty | ERROR | Unknown key (typo for 'observability'?) |
Errors: N | Warnings: M